Niclas Wesemann
Niclas Wesemann
I think we could batch process the faces and speed it up that way.. I tried doing that but had problems with a dynamic amount of faces as an input...
@hirwa145 this was asked before and i think it is a great idea. Let me know if you are interested to work on that
hey @shubham-shahh, cool! Thanks for contributing to this project! I am looking forward to see your implementation. I added you as a collaborator on the project, please add your code...
Try new release [jp4.4](https://github.com/nwesem/mtcnn_facenet_cpp_tensorRT/releases/tag/jp4.4) with Jetpack 4.4 and tensorflow 1.15 and let me know if that helped. Thanks
Hey prakharter, the jpgs were successfully read, the actual problem is your video device you are using as input. This repository depends on a video stream input (e.g. a camera...
I sadly don't have access to a jetson nano anymore, would you be able to try? There is also a branch for deepstream
yes it was working with 4.4, there is a release for that https://github.com/nwesem/mtcnn_facenet_cpp_tensorRT/releases/tag/jp4.4
while we're at it, I realized that we are missing dev dependencies. in particular we are missing `golang-go` and `protobuf-compiler` to make the tests succeed, do you agree that we...
MoM: * request for more comments to this discussion
hi @erikbosch can you elaborate a bit on this? Do you already have sth in mind how a signal like this would be defined? I could take some time to...